From Time and Place to Preference: LLM-Driven Geo-Temporal Context in Recommendations

• URL: http://arxiv.org/abs/2510.24430v1
• Date: Tue, 28 Oct 2025 13:57:23 GMT
• Title: From Time and Place to Preference: LLM-Driven Geo-Temporal Context in Recommendations
• Abstract summary: Most recommender systems treat timestamps as numeric or cyclical values, overlooking real-world context such as holidays, events, and seasonal patterns.<n>We propose a scalable framework that uses large language models (LLMs) to generate geo-temporal embeddings from only a timestamp and coarse location.
• Score: 3.402237483362839
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most recommender systems treat timestamps as numeric or cyclical values, overlooking real-world context such as holidays, events, and seasonal patterns. We propose a scalable framework that uses large language models (LLMs) to generate geo-temporal embeddings from only a timestamp and coarse location, capturing holidays, seasonal trends, and local/global events. We then introduce a geo-temporal embedding informativeness test as a lightweight diagnostic, demonstrating on MovieLens, LastFM, and a production dataset that these embeddings provide predictive signal consistent with the outcomes of full model integrations. Geo-temporal embeddings are incorporated into sequential models through (1) direct feature fusion with metadata embeddings or (2) an auxiliary loss that enforces semantic and geo-temporal alignment. Our findings highlight the need for adaptive or hybrid recommendation strategies, and we release a context-enriched MovieLens dataset to support future research.

Related papers

• Recovering Temporal and Geographic Signals from Language Model Embeddings [0.0]
  We study whether language-model embeddings encode structured real-world information.<n>We use a projection-based method that operates directly on output embeddings.<n>We find that embedding projections recover meaningful chronological and spatial structure.
  arXiv  Detail & Related papers  (2026-09-04T21:03:06Z)
• GeoGNN: Time Series Geo-Localization using Two-Tower Graph Neural Networks [11.28706377321882]
  Successful geolocalization can provide spatial context to time series, enabling location-aware applications.<n>We propose GeoGNN, a two-tower architecture for time series geolocalization.<n>Experiments on large-scale, countrywide electricity-consumption datasets demonstrate that GeoGNN achieves the best performance across datasets.
  arXiv  Detail & Related papers  (2026-06-06T19:10:56Z)
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI [52.13138825802668]
  GeoFMs are transforming Earth Observation, but evaluation lacks standardized protocols.<n> GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation.<n>Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license.
  arXiv  Detail & Related papers  (2025-11-19T17:45:02Z)
• ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting [16.98710098925001]
  Irregular intervals inherent to IMTS pose two core challenges for existing methods.<n>We propose the Adaptive Spatio-Temporal Graph Interaction (ASTGI) framework to address these challenges.<n>Experiments on multiple benchmark datasets demonstrate that ASTGI outperforms various state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-27T14:00:27Z)
• ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting [54.57031153712623]
  ARIES is a framework for assessing relation between time series properties and modeling strategies.<n>We propose the first deep forecasting model recommender, capable of providing interpretable suggestions for real-world time series.
  arXiv  Detail & Related papers  (2025-09-07T13:57:14Z)
• GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space [48.09196906704634]
  GT-Loc is a novel retrieval-based method that jointly predicts the capture time (hour and month) and geo-location (GPS coordinates) of an image.<n>Our approach employs separate encoders for images, time, and location, aligning their embeddings within a shared high-dimensional feature space.
  arXiv  Detail & Related papers  (2025-07-14T16:54:57Z)
• Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing [0.5120567378386615]
  Millions of biological sample records collected in the last few centuries archived in natural history collections are un-georeferenced.<n>We present preliminary experiments and results of a novel method that exploits multi-modal capabilities of recent Large Multi-Modal Models (LMM)<n>This method enables the model to visually contextualize spatial relations it reads in the locality description.
  arXiv  Detail & Related papers  (2025-07-11T13:23:25Z)
• TimeRefine: Temporal Grounding with Time Refining Video LLM [75.99665302872901]
  Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt.<n>We reformulate the temporal grounding task as a temporal refining task.<n>We incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth.
  arXiv  Detail & Related papers  (2024-12-12T18:59:11Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events [10.15184389811683]
  This paper introduces a novel retrieval-retrieval framework leveraging Large Language Models (LLMs) We propose a Geo-Time Re-ranking (GTR-ranking) strategy that identifies multi-faceted criteria including spatial proximity, temporal association, semantic similarity, and category-instructed similarity to rank similartemporal events. We apply the proposed framework to a dataset of four thousand Local Environmental Observer (LEO) Network events, achieving performance in recommending similar events among multiple cutting-edge dense retrieval models.
  arXiv  Detail & Related papers  (2024-11-19T21:57:22Z)
• Geolocation Representation from Large Language Models are Generic Enhancers for Spatio-Temporal Learning [10.438284728725842]
  Universal representation models are less prevalent than their extensive use in natural language processing and computer vision.<n>This discrepancy arises primarily from the high costs associated with the input of existing representation models.<n>We develop a training-free method that leverages large language models to derive geolocation representations.
  arXiv  Detail & Related papers  (2024-08-22T04:05:02Z)
• GeoLLM: Extracting Geospatial Knowledge from Large Language Models [49.20315582673223]
  We present GeoLLM, a novel method that can effectively extract geospatial knowledge from large language models. We demonstrate the utility of our approach across multiple tasks of central interest to the international community, including the measurement of population density and economic livelihoods. Our experiments reveal that LLMs are remarkably sample-efficient, rich in geospatial information, and robust across the globe.
  arXiv  Detail & Related papers  (2023-10-10T00:03:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.